Skip to content
ProductArena

Rank #4 of 4 in Data Warehouses & Lakehouses

MotherDuck logo

MotherDuck

Built-in AI assistant

MotherDuck (built on DuckDB) · commercial

motherduck.com ↗Try it →
PA Score37/100AGENT-READY56/100BUILT-IN AI56/100API30/100
MCP✓CLI~API✓
no public signals
ArenasData Warehouses & Lakehouses#4/4

Access

Open app ↗API docs ↗CLI docs ↗MCP docs ↗

Install

brewbrew install duckdb
installercurl https://install.duckdb.org | sh

Vendor-official, but review any script before piping it to a shell.

pippip install duckdb

Compare head-to-head

Snowflake logovs SnowflakeDatabricks logovs DatabricksBigQuery logovs BigQuery

Alternatives to MotherDuck →

Showcase

MotherDuck homepage screenshot
homepage · captured Sep 2026 · view live ↗
MotherDuck docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with MotherDuck before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$curl -s https://motherduck.com/.well-known/agent-skills/index.json | head -20recorded session — replayed, not live
recorded 2026-09-07 · exit 0 · captured verbatim by our probe harness, secrets redacted · pure-HTTP probe — ▶ run live re-runs it from our edge

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agent analytics — stories about agent analytics in this arenaAgent analyticsevidence →

Stories about agent analytics in this arena

72.7/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

51.4/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

15.0/100

Cost economics — stories about cost economics in this arenaCost economicsevidence →

Stories about cost economics in this arena

43.0/100

Ecosystem integrations — the surrounding ecosystem — integrations, marketplaces, community packagesEcosystem integrationsevidence →

The surrounding ecosystem — integrations, marketplaces, community packages

68.8/100

Governance access — stories about governance access in this arenaGovernance accessevidence →

Stories about governance access in this arena

12.0/100

Ingestion pipelines — stories about ingestion pipelines in this arenaIngestion pipelinesevidence →

Stories about ingestion pipelines in this arena

28.3/100

Notebooks workspace — stories about notebooks workspace in this arenaNotebooks workspaceevidence →

Stories about notebooks workspace in this arena

24.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

16.2/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Semantic layer — stories about semantic layer in this arenaSemantic layerevidence →

Stories about semantic layer in this arena

24.0/100

Sharing marketplace — stories about sharing marketplace in this arenaSharing marketplaceevidence →

Stories about sharing marketplace in this arena

53.3/100

Sql analytics — stories about sql analytics in this arenaSql analyticsevidence →

Stories about sql analytics in this arena

16.7/100

Streaming realtime — stories about streaming realtime in this arenaStreaming realtimeevidence →

Stories about streaming realtime in this arena

6.0/100

Story verdicts — every judged story with its evidenceStory verdicts

What’s free: 8 free · 0 paid · 0 enterprise · 28 not stated in evidence

?

Sorted by importance (agentic first) (high → low) · 54/54 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3fullfree9/10T⚿

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3fullfree9/10T⚿

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial7/10C

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3noneuntestednone yet

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2fullfree8/10T⚿

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T⚿

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T⚿

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2fullfree8/10T

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T⚿

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partialfree6/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10C

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1partial5/10T

My agent can run governed SQL end to end — authenticate, discover schemas, query, and read results back through a CLI or API with no dashboard in the loop C

Agent ops

ai-native userAgent analytics — stories about agent analytics in this arenaAgent analytics3fullfree8/10T⚿

The pricing model is documented clearly enough that I can estimate a monthly bill for my workload before committing G

Pricing

platform-engineerCost economics — stories about cost economics in this arenaCost economics3partial6/10C

Bulk-load CSV, JSON, and Parquet from cloud object storage with a single documented command C

Loading

data-engineerIngestion pipelines — stories about ingestion pipelines in this arenaIngestion pipelines3partial5/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial5/10T

I get a full analytical SQL surface — window functions, CTEs, semi-structured JSON, arrays, and rich date/time types — without bolt-on extensions C

Sql

analystSql analytics — stories about sql analytics in this arenaSql analytics3partial5/10T

Access control reaches tables, columns, and rows — roles plus masking policies — so one warehouse can serve many teams safely C

Access

platform-engineerGovernance access — stories about governance access in this arenaGovernance access3partial4/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3none0/10

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3none0/10

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3noneuntestednone yet

A built-in AI assistant writes, fixes, and explains SQL against my schemas from natural language, inside the product C

Agent ops

ai-native userAgent analytics — stories about agent analytics in this arenaAgent analytics2full8/10T⚿

Dbt is a first-class citizen — a documented adapter or native dbt project support with vendor docs to match C

Transformation

data-engineerEcosystem integrations — the surrounding ecosystem — integrations, marketplaces, community packagesEcosystem integrations2full8/10C

I get a fast local or free dev loop — a local engine, emulator, or sandbox — to develop transformations before touching production compute C

Dev loop

data-engineerEcosystem integrations — the surrounding ecosystem — integrations, marketplaces, community packagesEcosystem integrations2fullfree8/10T

Share live datasets with another account or organization without copying data or building an export pipeline C

Sharing

data-engineerSharing marketplace — stories about sharing marketplace in this arenaSharing marketplace2full8/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial6/10T⚿

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial6/10T

Budgets, resource monitors, or auto-suspend stop a runaway query or idle compute from burning money overnight G

Pricing

platform-engineerCost economics — stories about cost economics in this arenaCost economics2partial5/10C

First-party and partner connectors cover my sources — SaaS apps, databases, and ETL/ELT tools — with documented setup C

Connectors

data-engineerIngestion pipelines — stories about ingestion pipelines in this arenaIngestion pipelines2partial5/10C

Query open table formats and files in object storage — Iceberg, Delta, Parquet — without first loading them into proprietary storage C

Lakehouse

data-engineerSql analytics — stories about sql analytics in this arenaSql analytics2partial5/10C

A managed service continuously ingests new files or events as they arrive, without me running my own pipeline infrastructure C

Loading

data-engineerIngestion pipelines — stories about ingestion pipelines in this arenaIngestion pipelines2partial4/10C

Define a governed semantic model — metrics, dimensions, and joins declared once — that queries and AI tools answer against consistently C

Semantics

analystSemantic layer — stories about semantic layer in this arenaSemantic layer2partial4/10C

First-party notebooks let me mix SQL and Python against warehouse data, with results and charts inline C

Notebooks

analystNotebooks workspace — stories about notebooks workspace in this arenaNotebooks workspace2partial4/10X

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial4/10C

I get audit logs of who ran what and column-level lineage of where data came from G

Governance

platform-engineerGovernance access — stories about governance access in this arenaGovernance access2none0/10

Inspect query profiles and execution plans to find why a query is slow or expensive C

Performance

data-engineerSql analytics — stories about sql analytics in this arenaSql analytics2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Streaming writes land queryable within seconds through a documented streaming ingestion API C

Streaming

data-engineerStreaming realtime — stories about streaming realtime in this arenaStreaming realtime2noneuntestednone yet

Time-travel — query data as of a past point and restore dropped or corrupted tables from history C

Recovery

data-engineerSql analytics — stories about sql analytics in this arenaSql analytics2noneuntestednone yet

Evaluate with a free tier or trial — real queries on real data without a credit card or a sales call G

Trial

analystCost economics — stories about cost economics in this arenaCost economics1fullfree9/10T

Business users can ask questions in natural language and get governed, semantically-grounded answers rather than hallucinated joins C

Agent ops

ai-native userAgent analytics — stories about agent analytics in this arenaAgent analytics1partial6/10T⚿

Standard drivers (JDBC/ODBC) and documented BI-tool integrations connect my dashboards without custom glue C

Bi

analystEcosystem integrations — the surrounding ecosystem — integrations, marketplaces, community packagesEcosystem integrations1partial4/10C

Run continuous or incremental transformations — streams, tasks, declarative pipelines, or continuous queries — inside the platform C

Streaming

data-engineerStreaming realtime — stories about streaming realtime in this arenaStreaming realtime1partial3/10C

A marketplace of third-party datasets lets me enrich my own data directly inside the platform C

Sharing

analystSharing marketplace — stories about sharing marketplace in this arenaSharing marketplace1none0/10

Compliance attestations (SOC 2, HIPAA, PCI) are documented so security review does not stall the rollout C

Governance

platform-engineerGovernance access — stories about governance access in this arenaGovernance access1noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1noneuntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 40 stories with headroom

What would move MotherDuck’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".

  2. Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events

    nonemoves PA Scoreimpact 30

    Evidence shows scheduled Python jobs (time-based cron-style automation) but no capability for defining rules that trigger actions automatically on data or system events (e.g., event-driven triggers, alerts, webhooks on conditions).

  3. Openness — open source, data portability, and self-hosting storiesSelf-host the core product

    nonemoves PA Scoreimpact 30

    MotherDuck is explicitly a managed serverless cloud data warehouse; while DuckDB itself is open-source and can run locally, the core MotherDuck service (multi-tenant cloud engine, billing, sharing, dives, remote MCP) is not offered as a self-hosted deployment.

  4. Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models

    nonemoves PA Scoreimpact 30

    The evidence pack contains no statement about whether MotherDuck uses customer data to train AI models, nor any opt-out/data-training policy control; this is a fair question given MotherDuck's AI features (Dives, natural language MCP querying) but no documentation addresses it.

  5. Agenticness — how well agents can access and operate the productSubscribe to events via webhooks

    nonemoves agent-readyimpact 30

    Missing: any webhook endpoint registration, event-driven push notification system, or documentation of subscribable events.

  6. Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples

    nonemoves API qualityimpact 30

    Missing: an interactive API explorer page, runnable/live code examples, and any confirmation the OpenAPI spec is surfaced as a browsable interactive reference.

  7. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    Missing: any docs describing API version numbers, backward-compatibility guarantees, or a deprecation/sunset policy.

  8. Governance access — stories about governance access in this arenaI get audit logs of who ran what and column-level lineage of where data came from

    nonemoves PA Scoreimpact 20

    Missing: audit log documentation (who ran what query, when), column-level lineage tracking or metadata catalog, any independent verification of these governance features.

Showing the top 8 of 40 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map8 surfaces · 36 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

docs35 stories

GitHub README12 stories

llms.txt5 stories

OpenAPI spec4 stories

docs3 stories

Product docs3 stories

Hacker News2 stories

motherduck.com2 stories

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$curl -s https://motherduck.com/.well-known/agent-skills/index.json | head -20reproduced
$ curl -s https://motherduck.com/.well-known/agent-skills/index.json | head -20
{
  "$schema": "https://schemas.agentskills.io/discovery/0.2.0/schema.json",
  "skills": [
    {
      "name": "llms-txt",
      "type": "skill-md",
      "description": "Machine-readable site summaries for LLMs at /llms.txt and /llms-full.txt",
      "url": "/.well-known/agent-skills/llms-txt/SKILL.md",
      "digest": "sha256:2f0d3f0f7604d6bed95c4c03a585459a23f17efc6859cac08f63848582966854"
    },
    {
      "name": "markdown-negotiation",
      "type": "skill-md",
      "description": "Accept: text/markdown content negotiation for Markdown page responses",
      "url": "/.well-known/agent-skills/markdown-negotiation/SKILL.md",
      "digest": "sha256:6be46fc80b9186515ffb6dc3535ffa59e9e7a12a08959a26233e2f708a966116"
    },
    {
      "name": "api-and-mcp",
      "type": "skill-md",
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-07
$duckdb -c 'CREATE TABLE events AS SELECT ... FROM range(1000000); SELECT region, count(*), sum(revenue) FROM events GROUP BY region' # keyless in-memory enginereproduced
$ duckdb -c 'CREATE TABLE events AS SELECT ... FROM range(1000000); SELECT region, count(*), sum(revenue) FROM events GROUP BY region'  # [redacted]less in-memory engine
Timeout trying to read terminal background color (> 5s elapsed).
Disable terminal background color detection by using duckdb -dark-mode or duckdb -light-mode.
This likely means duckdb does not correctly support your CLI.
Please file an issue.
┌────────┬────────┬────────────────┐
│ region │   n    │ total_revenue  │
│ int64  │ int64  │ decimal(38,1)  │
├────────┼────────┼────────────────┤
│      0 │ 250000 │ 187499250000.0 │
│      1 │ 250000 │ 187499625000.0 │
│      2 │ 250000 │ 187500000000.0 │
│      3 │ 250000 │ 187500375000.0 │
└────────┴────────┴────────────────┘
proves: I get a fast local or free dev loop — a local engine, emulator, or sandbox — to develop transformations before touching production computeproves: I get a full analytical SQL surface — window functions, CTEs, semi-structured JSON, arrays, and rich date/time types — without bolt-on extensionsproves: Use an official CLIrecorded 2026-09-07
$printf '<initialize> <initialized> <tools/call execute_query GROUP BY>' | uvx mcp-server-motherduck --db-path :memory: --read-write # real SQL through MCP, keylessreproduced
$ printf '<initialize> <initialized> <tools/call execute_query GROUP BY>' | uvx mcp-server-motherduck --db-path :memory: --read-write  # real SQL through MCP, [redacted]less
{"jsonrpc":"2.0","id":2,"result":{"_meta":{"fastmcp":{"wrap_result":true}},"content":[{"text":"{\n  \"success\": true,\n  \"columns\": [\n    \"region\",\n    \"n\",\n    \"total\"\n  ],\n  \"columnTypes\": [\n    \"BIGINT\",\n    \"BIGINT\",\n    \"DECIMAL(38,1)\"\n  ],\n  \"rows\": [\n    [\n      0,\n      500,\n      \"374250.0\"\n    ],\n    [\n      1,\n      500,\n      \"375000.0\"\n    ]\n  ],\n  \"rowCount\": 2\n}","type":"text"}],"isError":false,"structuredContent":{"result":"{\n  \"success\": true,\n  \"columns\": [\n    \"region\",\n    \"n\",\n    \"total\"\n  ],\n  \"columnTypes\": [\n    \"BIGINT\",\n    \"BIGINT\",\n    \"DECIMAL(38,1)\"\n  ],\n  \"rows\": [\n    [\n      0,\n      500,\n      \"374250.0\"\n    ],\n    [\n      1,\n      500,\n      \"375000.0\"\n    ]\n  ],\n  \"rowCount\": 2\n}"}}}
proves: My agent can run governed SQL end to end — authenticate, discover schemas, query, and read results back through a CLI or API with no dashboard in the loopproves: Connect an agent via an official MCP serverproves: I get a fast local or free dev loop — a local engine, emulator, or sandbox — to develop transformations before touching production computerecorded 2026-09-07
$curl -si -X POST https://api.motherduck.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced
$ curl -si -X POST https://api.motherduck.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401

x-powered-by: Express

www-authenticate: Bearer resource_metadata="https://api.motherduck.com/.well-known/oauth-protected-resource/mcp", resource="https://api.motherduck.com/mcp"

content-type: application/json; charset=utf-8

content-length: 144

etag: W/"90-yPtacwdUU1ZrZyWM/1qM34Ur48c"

date: Mon, 07 Sep 2026 00:31:10 GMT

x-envoy-upstream-service-time: 1

server: envoy

{"jsonrpc":"2.0","error":{"code":-32001,"message":"Authentication required. Please authenticate using OAuth or provide a Bearer [redacted]."},"id":1}
proves: Connect an agent via an official MCP serverrecorded 2026-09-07
$printf '<jsonrpc initialize>' | uvx mcp-server-motherduck --db-path :memory: --read-write # stdio handshake, no accountreproduced
$ printf '<jsonrpc initialize>' | uvx mcp-server-motherduck --db-path :memory: --read-write  # stdio handshake, no account
{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2025-06-18","capabilities":{"logging":{},"prompts":{"listChanged":false},"resources":{"subscribe":false,"listChanged":false},"tools":{"listChanged":true}},"serverInfo":{"name":"mcp-server-motherduck","version":"1.0.8","icons":[{"src":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAcIAAAHCCAYAAAB8GMlFAAAX+ElEQVR4nO3d63UbV7Yu0M9nnP8XjuBUR9B0BIYjsD
proves: Connect an agent via an official MCP serverproves: My agent can run governed SQL end to end — authenticate, discover schemas, query, and read results back through a CLI or API with no dashboard in the looprecorded 2026-09-07

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

9 of 20 testable claims verified · 0 contradicted → integrity 45/100

33 distinct capability claims found in MotherDuck’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

9

Verified

11

Unverified

0

Contradicted

16

Undersold

Verified (11)
Unverified (16)
Undersold (16)
Claims outside our story set (6)

Real capability claims found in MotherDuck’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “Locally cache login credentials so CLI/Python sessions don't need to re-authenticate every time”

    source ↗

  • “SaaS Mode can restrict MotherDuck's ability to interact with the local environment”

    source ↗

  • “Sub-100ms cold start with read replicas for horizontal read scaling”

    source ↗

  • “Secrets (credentials) are scoped to the individual user account and not shared org-wide”

    source ↗

  • “Read scaling adds read-only Ducklings so concurrent users don't queue behind each other”

    source ↗

  • “Only a path: connection-string setting needs to change to point existing DuckDB tooling at MotherDuck”

    source ↗
Suggest a story for these →

Business model

free-tierusage-basedsubscription-flatenterprise-custom

Free tier (10 GB storage, 10 compute-hours/month, no card); Business is $250/month base plus per-second compute, compressed storage, and AI units; Enterprise is custom. Zero idle cost — instances stop when unused.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score37 (Sep 7 '26)37 (Sep 7 '26)
Agent-ready61 (Sep 7 '26)56 (Sep 7 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)
⚿ auth1 auth-gated probe

Agent surface uptime MCP 100% · llms.txt 100% · openapi.json 100% (30d, checked every 6h since Sep 8 '26)